Corona Virus (Covid 19) Visualisation and Prediction

Source: https://cdn.mos.cms.futurecdn.net/WxgePFJHTNAQRBuP3g5hoM-650-80.jpg.webp

Import libraries

import numpy as np 
import matplotlib.pyplot as plt 
import matplotlib.colors as mcolors
import pandas as pd 
import random
import math
import time
#---------------------------------------
from sklearn.linear_model import LinearRegression, BayesianRidge
from sklearn.model_selection import RandomizedSearchCV, train_test_split
from sklearn.preprocessing import PolynomialFeatures
from sklearn.svm import SVR
from sklearn.metrics import mean_squared_error, mean_absolute_error
#----------------------------------------------------------------------
import datetime
import operator 
plt.style.use('fivethirtyeight')
%matplotlib inline
import warnings
warnings.filterwarnings("ignore")

latest_data.head()

	FIPS	Admin2	Province_State	Country_Region	Last_Update	Lat	Long_	Confirmed	Deaths	Recovered	Active	Combined_Key	Incidence_Rate	Case-Fatality_Ratio
0	NaN	NaN	NaN	Afghanistan	2020-10-21 04:24:14	33.93911	67.709953	40369	1501	33790	5068.0	Afghanistan	103.669971	3.714349
1	NaN	NaN	NaN	Albania	2020-10-21 04:24:14	41.15330	20.168300	17651	458	10225	6968.0	Albania	613.350476	2.594754
2	NaN	NaN	NaN	Algeria	2020-10-21 04:24:14	28.03390	1.659600	54829	1873	38346	14610.0	Algeria	125.034654	3.416075
3	NaN	NaN	NaN	Andorra	2020-10-21 04:24:14	42.50630	1.521800	3623	62	2273	1288.0	Andorra	4689.057141	1.711289
4	NaN	NaN	NaN	Angola	2020-10-21 04:24:14	-11.20270	17.873900	8049	251	3037	4761.0	Angola	24.490155	3.118400

confirmed_df.head()

	Province/State	Country/Region	Lat	Long	1/22/20	1/23/20	1/24/20	1/25/20	1/26/20	1/27/20	...	12/24/20	12/25/20	12/26/20	12/27/20	12/28/20	12/29/20	12/30/20	12/31/20	1/1/21	1/2/21
0	NaN	Afghanistan	33.93911	67.709953	0	0	0	0	0	0	...	50655	50810	50886	51039	51280	51350	51405	51526	51526	51526
1	NaN	Albania	41.15330	20.168300	0	0	0	0	0	0	...	54827	55380	55755	56254	56572	57146	57727	58316	58316	58991
2	NaN	Algeria	28.03390	1.659600	0	0	0	0	0	0	...	97007	97441	97857	98249	98631	98988	99311	99610	99897	100159
3	NaN	Andorra	42.50630	1.521800	0	0	0	0	0	0	...	7699	7756	7806	7821	7875	7919	7983	8049	8117	8166
4	NaN	Angola	-11.20270	17.873900	0	0	0	0	0	0	...	17029	17099	17149	17240	17296	17371	17433	17553	17568	17608

5 rows × 351 columns

us_medical_data.head()

	Province_State	Country_Region	Last_Update	Lat	Long_	Confirmed	Deaths	Recovered	Active	FIPS	Incident_Rate	People_Tested	People_Hospitalized	Mortality_Rate	UID	ISO3	Testing_Rate	Hospitalization_Rate
0	Alabama	US	2020-10-21 04:30:32	32.3182	-86.9023	175210	2805	74238.0	97485.0	1.0	3559.482255	1265575.0	NaN	1.607192	84000001	USA	25811.283890	NaN
1	Alaska	US	2020-10-21 04:30:32	61.3707	-152.4044	11391	67	6681.0	4643.0	2.0	1557.115420	546525.0	NaN	0.588184	84000002	USA	74708.322796	NaN
2	American Samoa	US	2020-10-21 04:30:32	-14.2710	-170.1320	0	0	NaN	0.0	60.0	0.000000	1616.0	NaN	NaN	16	ASM	2904.333136	NaN
3	Arizona	US	2020-10-21 04:30:32	33.7298	-111.4312	232937	5837	38705.0	188395.0	4.0	3200.248066	1647345.0	NaN	2.505828	84000004	USA	22632.354026	NaN
4	Arkansas	US	2020-10-21 04:30:32	34.9697	-92.3731	100441	1728	90283.0	8430.0	5.0	3328.281094	1231652.0	NaN	1.720413	84000005	USA	40812.855971	NaN

cols = confirmed_df.keys()

print(cols)

Index(['Province/State', 'Country/Region', 'Lat', 'Long', '1/22/20', '1/23/20',
       '1/24/20', '1/25/20', '1/26/20', '1/27/20',
       ...
       '12/24/20', '12/25/20', '12/26/20', '12/27/20', '12/28/20', '12/29/20',
       '12/30/20', '12/31/20', '1/1/21', '1/2/21'],
      dtype='object', length=351)

Get all the dates for the outbreak

confirmed = confirmed_df.loc[:, cols[4]:cols[-1]]
deaths = deaths_df.loc[:, cols[4]:cols[-1]]
recoveries = recoveries_df.loc[:, cols[4]:cols[-1]]

dates = confirmed.keys()
world_cases = []
total_deaths = [] 
mortality_rate = []
recovery_rate = [] 
total_recovered = [] 
total_active = [] 

for i in dates:
    confirmed_sum = confirmed[i].sum()
    death_sum = deaths[i].sum()
    recovered_sum = recoveries[i].sum()
    
    # confirmed, deaths, recovered, and active
    world_cases.append(confirmed_sum)
    total_deaths.append(death_sum)
    total_recovered.append(recovered_sum)
    total_active.append(confirmed_sum-death_sum-recovered_sum)
    
    # calculate rates
    mortality_rate.append(death_sum/confirmed_sum)
    recovery_rate.append(recovered_sum/confirmed_sum)

Getting daily increases and moving averages

def daily_increase(data):
    d = [] 
    for i in range(len(data)):
        if i == 0:
            d.append(data[0])
        else:
            d.append(data[i]-data[i-1])
    return d 

def moving_average(data, window_size):
    moving_average = []
    for i in range(len(data)):
        if i + window_size < len(data):
            moving_average.append(np.mean(data[i:i+window_size]))
        else:
            moving_average.append(np.mean(data[i:len(data)]))
    return moving_average

# window size
window = 7

# confirmed cases
world_daily_increase = daily_increase(world_cases)
world_confirmed_avg= moving_average(world_cases, window)
world_daily_increase_avg = moving_average(world_daily_increase, window)

# deaths
world_daily_death = daily_increase(total_deaths)
world_death_avg = moving_average(total_deaths, window)
world_daily_death_avg = moving_average(world_daily_death, window)


# recoveries
world_daily_recovery = daily_increase(total_recovered)
world_recovery_avg = moving_average(total_recovered, window)
world_daily_recovery_avg = moving_average(world_daily_recovery, window)


# active 
world_active_avg = moving_average(total_active, window)

days_since_1_22 = np.array([i for i in range(len(dates))]).reshape(-1, 1)
world_cases = np.array(world_cases).reshape(-1, 1)
total_deaths = np.array(total_deaths).reshape(-1, 1)
total_recovered = np.array(total_recovered).reshape(-1, 1)

Future forcasting

days_in_future = 30
future_forcast = np.array([i for i in range(len(dates)+days_in_future)]).reshape(-1, 1)
adjusted_dates = future_forcast[:-30]

Convert integer into datetime for better visualization

start = '1/22/2020'
start_date = datetime.datetime.strptime(start, '%m/%d/%Y')
future_forcast_dates = []
for i in range(len(future_forcast)):
    future_forcast_dates.append((start_date + datetime.timedelta(days=i)).strftime('%m/%d/%Y'))

# slightly modify the data to fit the model better (regression models cannot pick the pattern)
X_train_confirmed, X_test_confirmed, y_train_confirmed, y_test_confirmed = train_test_split(days_since_1_22[50:], world_cases[50:], test_size=0.2, shuffle=False) 

Using SVM Regressor

# svm_confirmed = svm_search.best_estimator_
svm_confirmed = SVR(shrinking=True, kernel='poly',gamma=0.01, epsilon=1,degree=3, C=0.1)
svm_confirmed.fit(X_train_confirmed, y_train_confirmed)
svm_pred = svm_confirmed.predict(future_forcast)

# check against testing data
svm_test_pred = svm_confirmed.predict(X_test_confirmed)
plt.plot(y_test_confirmed)
plt.plot(svm_test_pred)
plt.legend(['Test Data', 'SVM Predictions'])
print('MAE:', mean_absolute_error(svm_test_pred, y_test_confirmed))
print('MSE:',mean_squared_error(svm_test_pred, y_test_confirmed))

MAE: 1326548.419556894
MSE: 1965217939383.6392

# transform our data for polynomial regression
poly = PolynomialFeatures(degree=4)
poly_X_train_confirmed = poly.fit_transform(X_train_confirmed)
poly_X_test_confirmed = poly.fit_transform(X_test_confirmed)
poly_future_forcast = poly.fit_transform(future_forcast)

bayesian_poly = PolynomialFeatures(degree=5)
bayesian_poly_X_train_confirmed = bayesian_poly.fit_transform(X_train_confirmed)
bayesian_poly_X_test_confirmed = bayesian_poly.fit_transform(X_test_confirmed)
bayesian_poly_future_forcast = bayesian_poly.fit_transform(future_forcast)

# polynomial regression
linear_model = LinearRegression(normalize=True, fit_intercept=False)
linear_model.fit(poly_X_train_confirmed, y_train_confirmed)
test_linear_pred = linear_model.predict(poly_X_test_confirmed)
linear_pred = linear_model.predict(poly_future_forcast)
print('MAE:', mean_absolute_error(test_linear_pred, y_test_confirmed))
print('MSE:',mean_squared_error(test_linear_pred, y_test_confirmed))

MAE: 7945015.295903881
MSE: 79185296204042.3

print(linear_model.coef_)

[[-1.38287451e+06  3.14448519e+04 -2.02859763e+02  3.88791621e+00
  -5.32255097e-03]]

plt.plot(y_test_confirmed)
plt.plot(test_linear_pred)
plt.legend(['Test Data', 'Polynomial Regression Predictions'])

<matplotlib.legend.Legend at 0x7fe6e68e3f10>

# bayesian ridge polynomial regression
tol = [1e-6, 1e-5, 1e-4, 1e-3, 1e-2]
alpha_1 = [1e-7, 1e-6, 1e-5, 1e-4, 1e-3]
alpha_2 = [1e-7, 1e-6, 1e-5, 1e-4, 1e-3]
lambda_1 = [1e-7, 1e-6, 1e-5, 1e-4, 1e-3]
lambda_2 = [1e-7, 1e-6, 1e-5, 1e-4, 1e-3]
normalize = [True, False]

bayesian_grid = {'tol': tol, 'alpha_1': alpha_1, 'alpha_2' : alpha_2, 'lambda_1': lambda_1, 'lambda_2' : lambda_2, 
                 'normalize' : normalize}

bayesian = BayesianRidge(fit_intercept=False)
bayesian_search = RandomizedSearchCV(bayesian, bayesian_grid, scoring='neg_mean_squared_error', cv=3, return_train_score=True, n_jobs=-1, n_iter=40, verbose=1)
bayesian_search.fit(bayesian_poly_X_train_confirmed, y_train_confirmed)

Fitting 3 folds for each of 40 candidates, totalling 120 fits

[Parallel(n_jobs=-1)]: Using backend LokyBackend with 4 concurrent workers.
[Parallel(n_jobs=-1)]: Done  48 tasks      | elapsed:    2.0s
[Parallel(n_jobs=-1)]: Done 120 out of 120 | elapsed:    2.1s finished

RandomizedSearchCV(cv=3, estimator=BayesianRidge(fit_intercept=False),
                   n_iter=40, n_jobs=-1,
                   param_distributions={'alpha_1': [1e-07, 1e-06, 1e-05, 0.0001,
                                                    0.001],
                                        'alpha_2': [1e-07, 1e-06, 1e-05, 0.0001,
                                                    0.001],
                                        'lambda_1': [1e-07, 1e-06, 1e-05,
                                                     0.0001, 0.001],
                                        'lambda_2': [1e-07, 1e-06, 1e-05,
                                                     0.0001, 0.001],
                                        'normalize': [True, False],
                                        'tol': [1e-06, 1e-05, 0.0001, 0.001,
                                                0.01]},
                   return_train_score=True, scoring='neg_mean_squared_error',
                   verbose=1)

bayesian_search.best_params_

{'tol': 0.001,
 'normalize': False,
 'lambda_2': 1e-06,
 'lambda_1': 0.001,
 'alpha_2': 0.001,
 'alpha_1': 1e-07}

bayesian_confirmed = bayesian_search.best_estimator_
test_bayesian_pred = bayesian_confirmed.predict(bayesian_poly_X_test_confirmed)
bayesian_pred = bayesian_confirmed.predict(bayesian_poly_future_forcast)
print('MAE:', mean_absolute_error(test_bayesian_pred, y_test_confirmed))
print('MSE:',mean_squared_error(test_bayesian_pred, y_test_confirmed))

MAE: 7142471.68637624
MSE: 63025963254224.75

plt.plot(y_test_confirmed)
plt.plot(test_bayesian_pred)
plt.legend(['Test Data', 'Bayesian Ridge Polynomial Predictions'])

<matplotlib.legend.Legend at 0x7fe6e6b11ad0>

Graphing the number of confirmed cases, active cases, deaths, recoveries, mortality rate (CFR), and recovery rate

# helper method for flattening the data, so it can be displayed on a bar graph 
def flatten(arr):
    a = [] 
    arr = arr.tolist()
    for i in arr:
        a.append(i[0])
    return a

adjusted_dates = adjusted_dates.reshape(1, -1)[0]
plt.figure(figsize=(16, 10))
plt.plot(adjusted_dates, world_cases)
plt.plot(adjusted_dates, world_confirmed_avg, linestyle='dashed', color='orange')
plt.title('# of Coronavirus Cases Over Time', size=30)
plt.xlabel('Days Since 1/22/2020', size=30)
plt.ylabel('# of Cases', size=30)
plt.legend(['Worldwide Coronavirus Cases', 'Moving Average {} Days'.format(window)], prop={'size': 20})
plt.xticks(size=20)
plt.yticks(size=20)
plt.show()

plt.figure(figsize=(16, 10))
plt.plot(adjusted_dates, total_deaths)
plt.plot(adjusted_dates, world_death_avg, linestyle='dashed', color='orange')
plt.title('# of Coronavirus Deaths Over Time', size=30)
plt.xlabel('Days Since 1/22/2020', size=30)
plt.ylabel('# of Cases', size=30)
plt.legend(['Worldwide Coronavirus Deaths', 'Moving Average {} Days'.format(window)], prop={'size': 20})
plt.xticks(size=20)
plt.yticks(size=20)
plt.show()

plt.figure(figsize=(16, 10))
plt.plot(adjusted_dates, total_recovered)
plt.plot(adjusted_dates, world_recovery_avg, linestyle='dashed', color='orange')
plt.title('# of Coronavirus Recoveries Over Time', size=30)
plt.xlabel('Days Since 1/22/2020', size=30)
plt.ylabel('# of Cases', size=30)
plt.legend(['Worldwide Coronavirus Recoveries', 'Moving Average {} Days'.format(window)], prop={'size': 20})
plt.xticks(size=20)
plt.yticks(size=20)
plt.show()

plt.figure(figsize=(16, 10))
plt.plot(adjusted_dates, total_active)
plt.plot(adjusted_dates, world_active_avg, linestyle='dashed', color='orange')
plt.title('# of Coronavirus Active Cases Over Time', size=30)
plt.xlabel('Days Since 1/22/2020', size=30)
plt.ylabel('# of Active Cases', size=30)
plt.legend(['Worldwide Coronavirus Active Cases', 'Moving Average {} Days'.format(window)], prop={'size': 20})
plt.xticks(size=20)
plt.yticks(size=20)
plt.show()

plt.figure(figsize=(16, 10))
plt.bar(adjusted_dates, world_daily_increase)
plt.plot(adjusted_dates, world_daily_increase_avg, color='orange', linestyle='dashed')
plt.title('World Daily Increases in Confirmed Cases', size=30)
plt.xlabel('Days Since 1/22/2020', size=30)
plt.ylabel('# of Cases', size=30)
plt.legend(['Moving Average {} Days'.format(window), 'World Daily Increase in COVID-19 Cases'], prop={'size': 20})
plt.xticks(size=20)
plt.yticks(size=20)
plt.show()

plt.figure(figsize=(16, 10))
plt.bar(adjusted_dates, world_daily_death)
plt.plot(adjusted_dates, world_daily_death_avg, color='orange', linestyle='dashed')
plt.title('World Daily Increases in Confirmed Deaths', size=30)
plt.xlabel('Days Since 1/22/2020', size=30)
plt.ylabel('# of Cases', size=30)
plt.legend(['Moving Average {} Days'.format(window), 'World Daily Increase in COVID-19 Deaths'], prop={'size': 20})
plt.xticks(size=20)
plt.yticks(size=20)
plt.show()

plt.figure(figsize=(16, 10))
plt.bar(adjusted_dates, world_daily_recovery)
plt.plot(adjusted_dates, world_daily_recovery_avg, color='orange', linestyle='dashed')
plt.title('World Daily Increases in Confirmed Recoveries', size=30)
plt.xlabel('Days Since 1/22/2020', size=30)
plt.ylabel('# of Cases', size=30)
plt.legend(['Moving Average {} Days'.format(window), 'World Daily Increase in COVID-19 Recoveries'], prop={'size': 20})
plt.xticks(size=20)
plt.yticks(size=20)
plt.show()

plt.figure(figsize=(16, 10))
plt.plot(adjusted_dates, np.log10(world_cases))
plt.title('Log of # of Coronavirus Cases Over Time', size=30)
plt.xlabel('Days Since 1/22/2020', size=30)
plt.ylabel('# of Cases', size=30)
plt.xticks(size=20)
plt.yticks(size=20)
plt.show()

plt.figure(figsize=(16, 10))
plt.plot(adjusted_dates, np.log10(total_deaths))
plt.title('Log of # of Coronavirus Deaths Over Time', size=30)
plt.xlabel('Days Since 1/22/2020', size=30)
plt.ylabel('# of Cases', size=30)
plt.xticks(size=20)
plt.yticks(size=20)
plt.show()

plt.figure(figsize=(16, 10))
plt.plot(adjusted_dates, np.log10(total_recovered))
plt.title('Log of # of Coronavirus Recoveries Over Time', size=30)
plt.xlabel('Days Since 1/22/2020', size=30)
plt.ylabel('# of Cases', size=30)
plt.xticks(size=20)
plt.yticks(size=20)
plt.show()

def country_plot(x, y1, y2, y3, y4, country):
    # window is set as 14 in in the beginning of the notebook 
    confirmed_avg = moving_average(y1, window)
    confirmed_increase_avg = moving_average(y2, window)
    death_increase_avg = moving_average(y3, window)
    recovery_increase_avg = moving_average(y4, window)
    
    plt.figure(figsize=(16, 10))
    plt.plot(x, y1)
    plt.plot(x, confirmed_avg, color='red', linestyle='dashed')
    plt.legend(['{} Confirmed Cases'.format(country), 'Moving Average {} Days'.format(window)], prop={'size': 20})
    plt.title('{} Confirmed Cases'.format(country), size=30)
    plt.xlabel('Days Since 1/22/2020', size=30)
    plt.ylabel('# of Cases', size=30)
    plt.xticks(size=20)
    plt.yticks(size=20)
    plt.show()

    plt.figure(figsize=(16, 10))
    plt.bar(x, y2)
    plt.plot(x, confirmed_increase_avg, color='red', linestyle='dashed')
    plt.legend(['Moving Average {} Days'.format(window), '{} Daily Increase in Confirmed Cases'.format(country)], prop={'size': 20})
    plt.title('{} Daily Increases in Confirmed Cases'.format(country), size=30)
    plt.xlabel('Days Since 1/22/2020', size=30)
    plt.ylabel('# of Cases', size=30)
    plt.xticks(size=20)
    plt.yticks(size=20)
    plt.show()

    plt.figure(figsize=(16, 10))
    plt.bar(x, y3)
    plt.plot(x, death_increase_avg, color='red', linestyle='dashed')
    plt.legend(['Moving Average {} Days'.format(window), '{} Daily Increase in Confirmed Deaths'.format(country)], prop={'size': 20})
    plt.title('{} Daily Increases in Deaths'.format(country), size=30)
    plt.xlabel('Days Since 1/22/2020', size=30)
    plt.ylabel('# of Cases', size=30)
    plt.xticks(size=20)
    plt.yticks(size=20)
    plt.show()

    plt.figure(figsize=(16, 10))
    plt.bar(x, y4)
    plt.plot(x, recovery_increase_avg, color='red', linestyle='dashed')
    plt.legend(['Moving Average {} Days'.format(window), '{} Daily Increase in Confirmed Recoveries'.format(country)], prop={'size': 20})
    plt.title('{} Daily Increases in Recoveries'.format(country), size=30)
    plt.xlabel('Days Since 1/22/2020', size=30)
    plt.ylabel('# of Cases', size=30)
    plt.xticks(size=20)
    plt.yticks(size=20)
    plt.show()
      
# helper function for getting country's cases, deaths, and recoveries        
def get_country_info(country_name):
    country_cases = []
    country_deaths = []
    country_recoveries = []  
    
    for i in dates:
        country_cases.append(confirmed_df[confirmed_df['Country/Region']==country_name][i].sum())
        country_deaths.append(deaths_df[deaths_df['Country/Region']==country_name][i].sum())
        country_recoveries.append(recoveries_df[recoveries_df['Country/Region']==country_name][i].sum())
    return (country_cases, country_deaths, country_recoveries)
    
    
def country_visualizations(country_name):
    country_info = get_country_info(country_name)
    country_cases = country_info[0]
    country_deaths = country_info[1]
    country_recoveries = country_info[2]
    
    country_daily_increase = daily_increase(country_cases)
    country_daily_death = daily_increase(country_deaths)
    country_daily_recovery = daily_increase(country_recoveries)
    
    country_plot(adjusted_dates, country_cases, country_daily_increase, country_daily_death, country_daily_recovery, country_name)
    

Country Specific Graphs

countries = ['Canada','Switzerland','Australia','US', 'Brazil','Australia''Italy'] 

for country in countries:
    country_visualizations(country)

# Country Comparison
# removed redundant code

compare_countries = ['Switzerland','Canada','US', 'Brazil','Australia'] 
graph_name = ['Coronavirus Confirmed Cases', 'Coronavirus Confirmed Deaths', 'Coronavirus Confirmed Recoveries']

for num in range(3):
    plt.figure(figsize=(16, 10))
    for country in compare_countries:
        plt.plot(get_country_info(country)[num])
    plt.legend(compare_countries, prop={'size': 20})
    plt.xlabel('Days since 3/1', size=30)
    plt.ylabel('# of Cases', size=30)
    plt.title(graph_name[num], size=30)
    plt.xticks(size=20)
    plt.yticks(size=20)
    plt.show()

def plot_predictions(x, y, pred, algo_name, color):
    plt.figure(figsize=(16, 10))
    plt.plot(x, y)
    plt.plot(future_forcast, pred, linestyle='dashed', color=color)
    plt.title('Worldwide Coronavirus Cases Over Time', size=30)
    plt.xlabel('Days Since 1/22/2020', size=30)
    plt.ylabel('# of Cases', size=30)
    plt.legend(['Confirmed Cases', algo_name], prop={'size': 20})
    plt.xticks(size=20)
    plt.yticks(size=20)
    plt.show()

Predictions for confirmed coronavirus cases worldwide

plot_predictions(adjusted_dates, world_cases, svm_pred, 'SVM Predictions', 'purple')

plot_predictions(adjusted_dates, world_cases, linear_pred, 'Polynomial Regression Predictions', 'orange')

plot_predictions(adjusted_dates, world_cases, bayesian_pred, 'Bayesian Ridge Regression Predictions', 'green')

# Future predictions using SVM 
svm_df = pd.DataFrame({'Date': future_forcast_dates[-10:], 'SVM Predicted # of Confirmed Cases Worldwide': np.round(svm_pred[-10:])})
svm_df.style.background_gradient(cmap='Reds')

	Date	SVM Predicted # of Confirmed Cases Worldwide
0	01/23/2021	103356037.000000
1	01/24/2021	104189868.000000
2	01/25/2021	105028244.000000
3	01/26/2021	105871175.000000
4	01/27/2021	106718675.000000
5	01/28/2021	107570757.000000
6	01/29/2021	108427432.000000
7	01/30/2021	109288712.000000
8	01/31/2021	110154611.000000
9	02/01/2021	111025140.000000

# Future predictions using polynomial regression
linear_pred = linear_pred.reshape(1,-1)[0]
linear_df = pd.DataFrame({'Date': future_forcast_dates[-10:], 'Polynomial Predicted # of Confirmed Cases Worldwide': np.round(linear_pred[-10:])})
linear_df.style.background_gradient(cmap='Reds')

	Date	Polynomial Predicted # of Confirmed Cases Worldwide
0	01/23/2021	78460389.000000
1	01/24/2021	78861293.000000
2	01/25/2021	79261726.000000
3	01/26/2021	79661664.000000
4	01/27/2021	80061084.000000
5	01/28/2021	80459962.000000
6	01/29/2021	80858273.000000
7	01/30/2021	81255993.000000
8	01/31/2021	81653097.000000
9	02/01/2021	82049563.000000

# Future predictions using Bayesian Ridge 
bayesian_df = pd.DataFrame({'Date': future_forcast_dates[-10:], 'Bayesian Ridge Predicted # of Confirmed Cases Worldwide': np.round(bayesian_pred[-10:])})
bayesian_df.style.background_gradient(cmap='Reds')

	Date	Bayesian Ridge Predicted # of Confirmed Cases Worldwide
0	01/23/2021	82173009.000000
1	01/24/2021	82674851.000000
2	01/25/2021	83178229.000000
3	01/26/2021	83683146.000000
4	01/27/2021	84189606.000000
5	01/28/2021	84697611.000000
6	01/29/2021	85207167.000000
7	01/30/2021	85718277.000000
8	01/31/2021	86230946.000000
9	02/01/2021	86745176.000000

Mortality Rate (worldwide) *susceptible to change

mean_mortality_rate = np.mean(mortality_rate)
plt.figure(figsize=(16, 10))
plt.plot(adjusted_dates, mortality_rate, color='orange')
plt.axhline(y = mean_mortality_rate,linestyle='--', color='black')
plt.title('Worldwide Mortality Rate of Coronavirus Over Time', size=30)
plt.xlabel('Days Since 1/22/2020', size=30)
plt.ylabel('Case Mortality Rate', size=30)
plt.xticks(size=20)
plt.yticks(size=20)
plt.show()

Recovery Rate (worldwide) suceptible to change

mean_recovery_rate = np.mean(recovery_rate)
plt.figure(figsize=(16, 10))
plt.plot(adjusted_dates, recovery_rate, color='blue')
plt.title('Worldwide Recovery Rate of Coronavirus Over Time', size=30)
plt.xlabel('Days Since 1/22/2020', size=30)
plt.ylabel('Case Recovery Rate', size=30)
plt.xticks(size=20)
plt.yticks(size=20)
plt.show()

Graphing deaths against recoveries

plt.figure(figsize=(16, 10))
plt.plot(adjusted_dates, total_deaths, color='r')
plt.plot(adjusted_dates, total_recovered, color='green')
plt.legend(['death', 'recoveries'], loc='best', fontsize=25)
plt.title('Worldwide Coronavirus Cases', size=30)
plt.xlabel('Days Since 1/22/2020', size=30)
plt.ylabel('# of Cases', size=30)
plt.xticks(size=20)
plt.yticks(size=20)
plt.show()

Plotting the number of deaths against the number of recoveries

plt.figure(figsize=(16, 10))
plt.plot(total_recovered, total_deaths)
plt.title('# of Coronavirus Deaths vs. # of Coronavirus Recoveries', size=30)
plt.xlabel('# of Coronavirus Recoveries', size=30)
plt.ylabel('# of Coronavirus Deaths', size=30)
plt.xticks(size=20)
plt.yticks(size=20)
plt.show()

Getting information about countries/regions that have confirmed coronavirus cases

unique_countries =  list(latest_data['Country_Region'].unique())

country_confirmed_cases = []
country_death_cases = [] 
country_active_cases = []
country_recovery_cases = []
country_incidence_rate = [] 
country_mortality_rate = [] 

no_cases = []
for i in unique_countries:
    cases = latest_data[latest_data['Country_Region']==i]['Confirmed'].sum()
    if cases > 0:
        country_confirmed_cases.append(cases)
    else:
        no_cases.append(i)
        
for i in no_cases:
    unique_countries.remove(i)
    
# sort countries by the number of confirmed cases
unique_countries = [k for k, v in sorted(zip(unique_countries, country_confirmed_cases), key=operator.itemgetter(1), reverse=True)]
for i in range(len(unique_countries)):
    country_confirmed_cases[i] = latest_data[latest_data['Country_Region']==unique_countries[i]]['Confirmed'].sum()
    country_death_cases.append(latest_data[latest_data['Country_Region']==unique_countries[i]]['Deaths'].sum())
    country_recovery_cases.append(latest_data[latest_data['Country_Region']==unique_countries[i]]['Recovered'].sum())
    country_active_cases.append(latest_data[latest_data['Country_Region']==unique_countries[i]]['Active'].sum())
    country_incidence_rate.append(latest_data[latest_data['Country_Region']==unique_countries[i]]['Incidence_Rate'].sum())
    country_mortality_rate.append(country_death_cases[i]/country_confirmed_cases[i])

Bar Chart Visualizations for COVID-19

total_world_cases = np.sum(country_confirmed_cases)
us_confirmed = latest_data[latest_data['Country_Region']=='US']['Confirmed'].sum()
outside_us_confirmed = total_world_cases - us_confirmed

plt.figure(figsize=(16, 9))
plt.barh('United States', us_confirmed)
plt.barh('Outside United States', outside_us_confirmed)
plt.title('# of Total Coronavirus Confirmed Cases', size=20)
plt.xticks(size=20)
plt.yticks(size=20)
plt.show()


plt.figure(figsize=(16, 9))
plt.barh('United States', us_confirmed/total_world_cases)
plt.barh('Outside United States', outside_us_confirmed/total_world_cases)
plt.title('# of Coronavirus Confirmed Cases Expressed in Percentage', size=20)
plt.xticks(size=20)
plt.yticks(size=20)
plt.show()

print('Outside United States {} cases:'.format(outside_us_confirmed))
print('United States {} cases'.format(us_confirmed))
print('Total: {} cases'.format(us_confirmed+outside_us_confirmed))

Outside United States 32548141 cases:
United States 8302170 cases
Total: 40850311 cases

# Only show 15 countries with the most confirmed cases, the rest are grouped into the other category
visual_unique_countries = [] 
visual_confirmed_cases = []
others = np.sum(country_confirmed_cases[10:])

for i in range(len(country_confirmed_cases[:10])):
    visual_unique_countries.append(unique_countries[i])
    visual_confirmed_cases.append(country_confirmed_cases[i])
    
visual_unique_countries.append('Others')
visual_confirmed_cases.append(others)

Visual Representations (bar charts and pie charts)

def plot_bar_graphs(x, y, title):
    plt.figure(figsize=(16, 12))
    plt.barh(x, y)
    plt.title(title, size=20)
    plt.xticks(size=20)
    plt.yticks(size=20)
    plt.show()
    
# good for a lot x values 
def plot_bar_graphs_tall(x, y, title):
    plt.figure(figsize=(19, 18))
    plt.barh(x, y)
    plt.title(title, size=25)
    plt.xticks(size=25)
    plt.yticks(size=25)
    plt.show()

plot_bar_graphs(visual_unique_countries, visual_confirmed_cases, '# of Covid-19 Confirmed Cases in Countries/Regions')

log_country_confirmed_cases = [math.log10(i) for i in visual_confirmed_cases]
plot_bar_graphs(visual_unique_countries, log_country_confirmed_cases, 'Common Log # of Coronavirus Confirmed Cases in Countries/Regions')

unique_provinces =  list(latest_data['Province_State'].unique())

Getting the latest information about provinces/states that have confirmed coronavirus cases

province_confirmed_cases = []
province_country = [] 
province_death_cases = [] 
# province_recovery_cases = []
province_active = [] 
province_incidence_rate = []
province_mortality_rate = [] 

no_cases = [] 
for i in unique_provinces:
    cases = latest_data[latest_data['Province_State']==i]['Confirmed'].sum()
    if cases > 0:
        province_confirmed_cases.append(cases)
    else:
        no_cases.append(i)
 
# remove areas with no confirmed cases
for i in no_cases:
    unique_provinces.remove(i)
    
unique_provinces = [k for k, v in sorted(zip(unique_provinces, province_confirmed_cases), key=operator.itemgetter(1), reverse=True)]
for i in range(len(unique_provinces)):
    province_confirmed_cases[i] = latest_data[latest_data['Province_State']==unique_provinces[i]]['Confirmed'].sum()
    province_country.append(latest_data[latest_data['Province_State']==unique_provinces[i]]['Country_Region'].unique()[0])
    province_death_cases.append(latest_data[latest_data['Province_State']==unique_provinces[i]]['Deaths'].sum())
#     province_recovery_cases.append(latest_data[latest_data['Province_State']==unique_provinces[i]]['Recovered'].sum())
    province_active.append(latest_data[latest_data['Province_State']==unique_provinces[i]]['Active'].sum())
    province_incidence_rate.append(latest_data[latest_data['Province_State']==unique_provinces[i]]['Incidence_Rate'].sum())
    province_mortality_rate.append(province_death_cases[i]/province_confirmed_cases[i])

# number of cases per province/state/city top 100 
province_limit = 100 
province_df = pd.DataFrame({'Province/State Name': unique_provinces[:province_limit], 'Country': province_country[:province_limit], 'Number of Confirmed Cases': province_confirmed_cases[:province_limit],
                          'Number of Deaths': province_death_cases[:province_limit],'Number of Active Cases' : province_active[:province_limit], 
                            'Incidence Rate' : province_incidence_rate[:province_limit], 'Mortality Rate': province_mortality_rate[:province_limit]})
# number of cases per country/region

province_df.style.background_gradient(cmap='Oranges')

	Province/State Name	Country	Number of Confirmed Cases	Number of Deaths	Number of Active Cases	Incidence Rate	Mortality Rate
0	Maharashtra	India	1609516	42453	174755.000000	1307.017058	0.026376
1	Sao Paulo	Brazil	1068962	38246	122517.000000	2327.927131	0.035779
2	California	US	883746	17055	866691.000000	101792.633443	0.019299
3	Texas	US	870347	17629	844719.000000	642622.496614	0.020255
4	Andhra Pradesh	India	789553	6481	33396.000000	1464.755660	0.008208
5	Karnataka	India	776901	10608	103964.000000	1149.896557	0.013654
6	Florida	US	760389	16105	744284.000000	266979.355801	0.021180
7	Tamil Nadu	India	694030	10741	36734.000000	891.596484	0.015476
8	England	United Kingdom	647025	38996	608029.000000	1155.872391	0.060270
9	New York	US	490166	33582	453114.000000	75039.637823	0.068511
10	Uttar Pradesh	India	459154	6714	30416.000000	193.016958	0.014623
11	Lima	Peru	394933	15212	379721.000000	3715.792445	0.038518
12	Moscow	Russia	372628	6058	88962.000000	2979.482297	0.016258
13	Illinois	US	354457	9537	344920.000000	225801.931860	0.026906
14	Kerala	India	353472	1206	92023.000000	990.133095	0.003412
15	Georgia	US	342438	7674	334764.000000	548043.120834	0.022410
16	Minas Gerais	Brazil	338107	8483	43344.000000	1597.195607	0.025090
17	Bahia	Brazil	337994	7363	19577.000000	2272.524343	0.021784
18	Delhi	India	336750	6081	23922.000000	1799.750969	0.018058
19	West Bengal	India	329057	6180	35170.000000	330.347658	0.018781
20	Capital District	Colombia	299713	7345	23213.000000	4043.309699	0.024507
21	Metropolitana	Chile	293436	9650	3191.000000	4125.459312	0.032886
22	Rio de Janeiro	Brazil	292621	19836	13857.000000	1694.885410	0.067787
23	Madrid	Spain	283130	10059	232335.000000	4262.947349	0.035528
24	Odisha	India	272250	1168	18885.000000	587.298383	0.004290
25	Ceara	Brazil	266289	9218	33790.000000	2915.973779	0.034617
26	North Carolina	US	248750	3992	244758.000000	243104.981892	0.016048
27	Para	Brazil	242129	6686	13446.000000	2814.515862	0.027613
28	Goias	Brazil	240165	5444	16544.000000	3421.956202	0.022668
29	Santa Catarina	Brazil	237781	2991	21295.000000	3318.744393	0.012579
30	Tennessee	US	233569	2952	230617.000000	352427.400653	0.012639
31	Arizona	US	232937	5837	227101.000000	49699.421894	0.025058
32	Punjab	India	230526	6356	7241.000000	519.281512	0.027572
33	Telangana	India	226124	1287	20449.000000	574.462159	0.005692
34	Rio Grande do Sul	Brazil	225694	5452	21554.000000	1983.732609	0.024157
35	New Jersey	US	222193	16227	205966.000000	46531.730006	0.073031
36	Bihar	India	207405	1011	11348.000000	166.190002	0.004875
37	Distrito Federal	Brazil	206265	3575	12883.000000	6840.685471	0.017332
38	Assam	India	202073	884	26775.000000	567.508576	0.004375
39	Parana	Brazil	201877	4999	56778.000000	1765.591737	0.024763
40	Pennsylvania	US	189970	8516	181454.000000	67604.603834	0.044828
41	Wisconsin	US	187828	1633	176849.000000	195583.720282	0.008694
42	Ohio	US	185639	5083	180556.000000	120884.690444	0.027381
43	Maranhao	Brazil	182020	3949	10945.000000	2572.655032	0.021695
44	Catalonia	Spain	179552	5919	147430.000000	2373.007829	0.032965
45	Rajasthan	India	177123	1774	20254.000000	218.582158	0.010016
46	Louisiana	US	176681	5772	170909.000000	266278.244651	0.032669
47	Alabama	US	175210	2805	171723.000000	261349.190923	0.016009
48	Amazonas	Brazil	171504	4701	44149.000000	11059.067568	0.027410
49	Virginia	US	167754	3485	163788.000000	261165.378883	0.020774
50	Michigan	US	165994	7383	158611.000000	92792.378118	0.044478
51	South Carolina	US	165493	3696	161797.000000	156224.781893	0.022333
52	Chhattisgarh	India	165279	1584	25709.000000	561.481529	0.009584
53	Madhya Pradesh	India	162178	2811	12507.000000	189.995275	0.017333
54	Missouri	US	161849	2625	159224.000000	271395.557107	0.016219
55	Gujarat	India	161686	3651	14245.000000	253.139075	0.022581
56	Pernambuco	Brazil	156794	8505	17154.000000	1640.607253	0.054243
57	Haryana	India	152174	1660	10078.000000	539.534344	0.010909
58	Indiana	US	150664	4008	146656.000000	176203.364962	0.026602
59	Ciudad de Mexico	Mexico	149109	14480	9159.000000	1653.341494	0.097110
60	Espirito Santo	Brazil	146233	3740	14658.000000	3638.858821	0.025576
61	Antioquia	Colombia	146086	2878	9223.000000	2280.063592	0.019701
62	Massachusetts	US	145464	9758	135706.000000	21221.281063	0.067082
63	Sindh	Pakistan	142348	2587	4267.000000	297.264020	0.018174
64	Maryland	US	136744	4050	132694.000000	42582.380890	0.029617
65	Mato Grosso	Brazil	136579	3690	20671.000000	3919.653686	0.027017
66	Lombardia	Italy	130479	17103	26304.000000	1296.933952	0.131079
67	Paraiba	Brazil	129045	3010	24962.000000	3211.570963	0.023325
68	Minnesota	US	125531	2299	123232.000000	177406.003989	0.018314
69	Mississippi	US	111322	3202	108120.000000	349563.593841	0.028763
70	Oklahoma	US	109548	1191	108357.000000	197035.225800	0.010872
71	Iowa	US	109202	1576	107626.000000	316262.046215	0.014432
72	Piaui	Brazil	106908	2304	5349.000000	3266.134613	0.021551
73	Washington	US	101864	2237	96868.000000	53489.461882	0.021961
74	Arkansas	US	100441	1728	98713.000000	256353.408944	0.017204
75	Jharkhand	India	97414	849	6180.000000	252.407450	0.008715
76	Utah	US	96643	551	96092.000000	31900.032580	0.005701
77	Andalusia	Spain	96224	2176	83377.000000	1141.798691	0.022614
78	Quebec	Canada	95216	6055	8693.000000	1115.245206	0.063592
79	Nordrhein-Westfalen	Germany	94883	1970	20106.000000	529.107492	0.020762
80	Mexico	Mexico	92547	10285	2889.000000	531.031186	0.111133
81	Nevada	US	91499	1727	89772.000000	19124.917987	0.018875
82	Alagoas	Brazil	89644	2187	1900.000000	2686.077636	0.024397
83	Kentucky	US	89544	1342	88202.000000	201824.614662	0.014987
84	Jammu and Kashmir	India	88958	1397	8124.000000	653.799117	0.015704
85	Colorado	US	87582	2182	85377.000000	73942.378940	0.024914
86	Sergipe	Brazil	82301	2145	7126.000000	3580.334242	0.026063
87	Bayern	Germany	82102	2726	11535.000000	627.848526	0.033203
88	Moscow Oblast	Russia	81377	1490	19135.000000	1084.537179	0.018310
89	Rio Grande do Norte	Brazil	78704	2553	34111.000000	2244.291392	0.032438
90	Mato Grosso do Sul	Brazil	77943	1512	7802.000000	2804.728055	0.019399
91	Kansas	US	76048	895	71284.000000	249620.681021	0.011769
92	Valle del Cauca	Colombia	75172	2603	5620.000000	1679.488709	0.034627
93	Tocantins	Brazil	73065	1055	16311.000000	4645.341688	0.014439
94	Zuid-Holland	Netherlands	71770	1536	70234.000000	1935.181530	0.021402
95	Atlantico	Colombia	69991	3110	1233.000000	2760.423219	0.044434
96	Rondonia	Brazil	69332	1429	7714.000000	3901.138010	0.020611
97	Ontario	Canada	68556	3107	6114.000000	465.992429	0.045321
98	Hubei	China	68139	4512	0.000000	115.158019	0.066218
99	Castilla y Leon	Spain	65158	3380	53062.000000	2706.197074	0.051874

# Only show 10 provinces with the most confirmed cases, the rest are grouped into the other category
visual_unique_provinces = [] 
visual_confirmed_cases2 = []
others = np.sum(province_confirmed_cases[10:])
for i in range(len(province_confirmed_cases[:10])):
    visual_unique_provinces.append(unique_provinces[i])
    visual_confirmed_cases2.append(province_confirmed_cases[i])

visual_unique_provinces.append('Others')
visual_confirmed_cases2.append(others)

plot_bar_graphs(visual_unique_provinces, visual_confirmed_cases2, '# of Coronavirus Confirmed Cases in Provinces/States')

log_province_confirmed_cases = [math.log10(i) for i in visual_confirmed_cases2]
plot_bar_graphs(visual_unique_provinces, log_province_confirmed_cases, 'Log of # of Coronavirus Confirmed Cases in Provinces/States')

Pie Chart Visualizations for COVID-19

def plot_pie_charts(x, y, title):
    # more muted color 
    c = ['lightcoral', 'rosybrown', 'sandybrown', 'navajowhite', 'gold',
        'khaki', 'lightskyblue', 'turquoise', 'lightslategrey', 'thistle', 'pink']
    plt.figure(figsize=(20,15))
    plt.title(title, size=20)
    plt.pie(y, colors=c,shadow=True, labels=y)
    plt.legend(x, loc='best', fontsize=12)
    plt.show()

plot_pie_charts(visual_unique_countries, visual_confirmed_cases, 'Covid-19 Confirmed Cases per Country')

plot_pie_charts(visual_unique_provinces, visual_confirmed_cases2, 'Covid-19 Confirmed Cases per State/Province/Region')

# Plotting countries with regional data using a pie chart 

def plot_pie_country_with_regions(country_name, title):
    regions = list(latest_data[latest_data['Country_Region']==country_name]['Province_State'].unique())
    confirmed_cases = []
    no_cases = [] 
    for i in regions:
        cases = latest_data[latest_data['Province_State']==i]['Confirmed'].sum()
        if cases > 0:
            confirmed_cases.append(cases)
        else:
            no_cases.append(i)

    # remove areas with no confirmed cases
    for i in no_cases:
        regions.remove(i)

    # only show the top 5 states
    regions = [k for k, v in sorted(zip(regions, confirmed_cases), key=operator.itemgetter(1), reverse=True)]

    for i in range(len(regions)):
        confirmed_cases[i] = latest_data[latest_data['Province_State']==regions[i]]['Confirmed'].sum()  
    
    # additional province/state will be considered "others"
    
    if(len(regions)>5):
        regions_5 = regions[:5]
        regions_5.append('Others')
        confirmed_cases_5 = confirmed_cases[:5]
        confirmed_cases_5.append(np.sum(confirmed_cases[5:]))
        plot_pie_charts(regions_5,confirmed_cases_5, title)
    else:
        plot_pie_charts(regions,confirmed_cases, title)

pie_chart_countries = ['Switzerland','Canada','Singapore','US','Australia',  'Germany','United Kingdom']

for i in pie_chart_countries:
    plot_pie_country_with_regions(i, 'Covid-19 Confirmed Cases in {}'.format(i))

US Medical Data on Testing

# Replace nan with 0
us_medical_data.fillna(value=0, inplace=True)

def plot_us_medical_data():
    states = us_medical_data['Province_State'].unique()
    testing_number = []
    testing_rate = []
    
    for i in states:
        testing_number.append(us_medical_data[us_medical_data['Province_State']==i]['People_Tested'].sum())
        testing_rate.append(us_medical_data[us_medical_data['Province_State']==i]['Testing_Rate'].max())
    
    # only show the top 15 states
    testing_states = [k for k, v in sorted(zip(states, testing_number), key=operator.itemgetter(1), reverse=True)]
    testing_rate_states = [k for k, v in sorted(zip(states, testing_rate), key=operator.itemgetter(1), reverse=True)]
  
    for i in range(len(states)):
        testing_number[i] = us_medical_data[us_medical_data['Province_State']==testing_states[i]]['People_Tested'].sum()
        testing_rate[i] = us_medical_data[us_medical_data['Province_State']==testing_rate_states[i]]['Testing_Rate'].sum()
    
    top_limit = 30 
    
    plot_bar_graphs_tall(testing_states[:top_limit], testing_number[:top_limit], 'Total Testing per State (Top 30)')
    plot_bar_graphs_tall(testing_rate_states[:top_limit], testing_rate[:top_limit], 'Testing Rate per 100,000 People (Top 30)')
 

plot_us_medical_data()